ChatGPT's predictions for chest pain cases were inconsistent, offering varied heart risk assessments ranging from low to intermediate, and occasionally high risk.
While OpenAI’s ChatGPT demonstrates proficiency in various medical assessments, it exhibits limitations in evaluating heart risk (1✔ ✔Trusted Source
ChatGPT provides inconsistent risk-stratification of patients with atraumatic chest pain
Go to source).
ChatGPT’s Reliability Questioned in Critical Health Assessments
Research, published in the journal PLOS ONE, showed that “it would be unwise to rely on it for some health assessments, such as whether a patient with chest pain needs to be hospitalized”.‘#ChatGPT's predictions for patients with #chestpain were found to be inconsistent, often assigning varying levels of #heartrisk assessment, ranging from low to intermediate, and occasionally high, for the same patient data.’
The variation “can be dangerous” said lead author Dr. Thomas Heston, a researcher with Washington State University’s Elson S. Floyd College of Medicine. Further, the generative AI system also failed to match the traditional methods physicians use to judge a patient’s cardiac risk. “ChatGPT was not acting in a consistent manner,” said Heston.
However, Heston sees great potential for generative AI in healthcare, but with further development.
“It can be a useful tool, but I think the technology is going a lot faster than our understanding of it, so it’s critically important that we do a lot of research, especially in these high-stakes clinical situations.”
Reference:
- ChatGPT provides inconsistent risk-stratification of patients with atraumatic chest pain - (https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0301854)
Source-IANS